{ "metadata": { "total_parameters": 16122254576, "total_size": 19164721504 }, "weight_map": { "lm_head.weight": "model-00004-of-00004.safetensors", "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.0.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.1.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.10.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.11.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.12.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.13.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.14.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.15.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.16.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.17.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.18.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.19.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.2.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.20.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.21.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.22.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.gate_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.mlp.gate.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.k_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.k_proj.k_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.k_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.o_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.o_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.q_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.q_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.v_proj.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.v_proj.v_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.23.self_attn.v_proj.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.24.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.25.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.26.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.27.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.28.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.29.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.3.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.30.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.31.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.32.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.33.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.34.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.35.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.input_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.down_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.36.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.gate_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.0.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.0.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.0.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.0.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.1.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.1.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.1.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.1.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.10.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.10.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.10.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.10.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.100.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.100.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.100.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.100.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.101.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.101.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.101.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.101.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.102.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.102.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.102.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.102.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.103.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.103.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.103.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.103.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.104.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.104.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.104.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.104.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.105.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.105.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.105.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.105.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.106.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.106.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.106.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.106.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.107.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.107.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.107.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.107.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.108.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.108.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.108.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.108.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.109.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.109.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.109.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.109.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.11.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.11.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.11.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.11.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.110.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.110.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.110.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.110.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.111.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.111.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.111.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.111.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.112.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.112.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.112.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.112.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.113.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.113.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.113.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.113.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.114.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.114.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.114.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.114.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.115.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.115.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.115.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.115.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.116.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.116.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.116.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.116.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.117.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.117.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.117.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.117.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.118.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.118.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.118.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.118.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.119.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.119.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.119.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.119.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.12.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.12.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.12.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.12.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.120.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.120.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.120.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.120.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.121.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.121.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.121.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.121.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.122.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.122.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.122.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.122.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.123.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.123.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.123.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.123.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.124.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.124.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.124.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.124.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.125.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.125.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.125.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.125.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.126.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.126.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.126.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.126.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.127.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.127.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.127.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.127.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.13.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.13.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.13.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.13.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.14.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.14.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.14.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.14.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.15.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.15.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.15.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.15.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.16.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.16.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.16.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.16.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.17.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.17.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.17.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.17.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.18.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.18.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.18.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.18.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.19.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.19.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.19.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.19.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.2.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.2.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.2.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.2.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.20.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.20.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.20.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.20.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.21.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.21.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.21.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.21.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.22.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.22.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.22.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.22.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.23.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.23.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.23.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.23.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.24.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.24.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.24.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.24.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.25.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.25.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.25.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.25.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.26.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.26.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.26.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.26.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.27.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.27.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.27.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.27.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.28.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.28.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.28.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.28.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.29.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.29.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.29.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.29.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.3.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.3.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.3.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.3.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.30.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.30.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.30.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.30.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.31.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.31.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.31.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.31.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.32.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.32.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.32.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.32.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.33.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.33.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.33.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.33.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.34.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.34.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.34.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.34.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.35.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.35.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.35.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.35.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.36.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.36.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.36.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.36.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.37.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.37.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.37.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.37.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.38.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.38.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.38.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.38.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.39.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.39.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.39.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.39.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.4.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.4.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.4.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.4.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.40.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.40.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.40.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.40.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.41.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.41.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.41.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.41.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.42.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.42.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.42.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.42.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.43.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.43.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.43.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.43.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.44.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.44.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.44.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.44.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.45.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.45.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.45.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.45.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.46.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.46.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.46.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.46.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.47.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.47.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.47.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.47.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.48.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.48.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.48.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.48.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.49.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.49.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.49.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.49.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.5.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.5.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.5.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.5.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.50.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.50.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.50.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.50.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.51.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.51.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.51.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.51.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.52.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.52.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.52.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.52.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.53.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.53.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.53.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.53.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.54.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.54.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.54.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.54.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.55.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.55.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.55.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.55.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.56.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.56.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.56.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.56.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.57.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.57.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.57.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.57.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.58.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.58.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.58.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.58.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.59.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.59.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.59.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.59.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.6.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.6.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.6.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.6.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.60.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.60.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.60.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.60.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.61.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.61.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.61.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.61.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.62.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.62.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.62.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.62.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.63.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.63.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.63.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.63.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.64.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.64.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.64.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.64.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.65.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.65.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.65.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.65.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.66.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.66.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.66.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.66.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.67.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.67.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.67.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.67.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.68.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.68.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.68.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.68.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.69.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.69.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.69.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.69.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.7.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.7.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.7.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.7.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.70.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.70.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.70.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.70.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.71.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.71.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.71.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.71.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.72.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.72.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.72.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.72.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.73.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.73.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.73.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.73.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.74.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.74.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.74.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.74.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.75.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.75.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.75.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.75.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.76.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.76.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.76.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.76.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.77.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.77.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.77.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.77.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.78.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.78.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.78.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.78.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.79.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.79.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.79.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.79.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.8.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.8.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.8.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.8.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.80.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.80.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.80.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.80.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.81.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.81.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.81.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.81.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.82.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.82.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.82.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.82.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.83.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.83.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.83.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.83.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.84.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.84.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.84.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.84.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.85.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.85.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.85.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.85.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.86.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.86.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.86.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.86.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.87.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.87.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.87.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.87.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.88.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.88.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.88.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.88.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.89.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.89.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.89.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.89.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.9.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.9.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.9.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.9.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.90.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.90.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.90.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.90.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.91.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.91.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.91.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.91.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.92.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.92.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.92.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.92.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.93.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.93.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.93.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.93.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.94.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.94.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.94.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.94.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.95.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.95.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.95.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.95.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.96.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.96.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.96.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.96.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.97.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.97.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.97.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.97.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.98.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.98.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.98.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.98.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.99.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.99.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.99.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.experts.up_proj.99.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.mlp.gate.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.37.self_attn.k_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.k_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.k_proj.k_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.k_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.k_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.o_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.o_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.o_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.q_norm.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.q_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.q_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.q_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.v_proj.input_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.v_proj.v_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.v_proj.weight_scale": "model-00003-of-00004.safetensors", "model.language_model.layers.37.self_attn.v_proj.weight_scale_2": "model-00003-of-00004.safetensors", "model.language_model.layers.38.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.38.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.39.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.4.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.40.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.40.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.41.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.42.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.43.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.44.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.45.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.46.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.input_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.down_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.gate_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.0.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.0.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.0.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.0.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.1.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.1.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.1.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.1.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.10.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.10.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.10.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.10.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.100.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.100.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.100.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.100.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.101.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.101.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.101.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.101.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.102.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.102.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.102.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.102.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.103.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.103.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.103.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.103.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.104.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.104.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.104.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.104.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.105.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.105.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.105.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.105.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.106.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.106.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.106.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.106.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.107.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.107.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.107.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.107.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.108.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.108.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.108.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.108.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.109.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.109.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.109.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.109.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.11.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.11.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.11.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.11.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.110.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.110.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.110.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.110.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.111.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.111.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.111.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.111.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.112.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.112.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.112.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.112.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.113.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.113.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.113.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.113.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.114.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.114.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.114.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.114.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.115.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.115.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.115.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.115.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.116.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.116.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.116.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.116.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.117.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.117.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.117.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.117.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.118.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.118.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.118.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.118.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.119.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.119.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.119.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.119.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.12.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.12.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.12.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.12.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.120.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.120.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.120.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.120.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.121.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.121.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.121.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.121.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.122.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.122.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.122.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.122.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.123.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.123.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.123.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.123.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.124.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.124.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.124.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.124.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.125.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.125.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.125.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.125.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.126.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.126.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.126.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.126.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.127.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.127.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.127.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.127.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.13.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.13.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.13.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.13.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.14.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.14.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.14.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.14.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.15.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.15.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.15.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.15.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.16.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.16.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.16.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.16.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.17.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.17.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.17.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.17.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.18.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.18.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.18.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.18.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.19.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.19.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.19.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.19.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.2.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.2.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.2.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.2.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.20.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.20.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.20.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.20.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.21.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.21.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.21.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.21.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.22.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.22.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.22.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.22.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.23.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.23.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.23.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.23.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.24.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.24.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.24.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.24.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.25.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.25.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.25.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.25.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.26.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.26.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.26.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.26.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.27.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.27.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.27.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.27.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.28.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.28.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.28.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.28.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.29.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.29.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.29.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.29.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.3.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.3.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.3.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.3.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.30.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.30.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.30.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.30.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.31.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.31.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.31.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.31.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.32.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.32.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.32.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.32.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.33.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.33.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.33.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.33.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.34.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.34.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.34.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.34.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.35.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.35.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.35.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.35.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.36.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.36.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.36.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.36.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.37.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.37.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.37.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.37.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.38.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.38.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.38.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.38.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.39.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.39.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.39.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.39.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.4.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.4.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.4.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.4.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.40.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.40.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.40.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.40.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.41.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.41.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.41.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.41.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.42.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.42.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.42.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.42.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.43.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.43.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.43.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.43.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.44.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.44.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.44.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.44.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.45.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.45.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.45.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.45.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.46.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.46.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.46.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.46.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.47.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.47.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.47.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.47.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.48.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.48.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.48.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.48.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.49.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.49.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.49.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.49.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.5.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.5.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.5.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.5.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.50.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.50.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.50.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.50.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.51.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.51.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.51.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.51.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.52.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.52.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.52.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.52.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.53.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.53.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.53.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.53.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.54.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.54.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.54.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.54.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.55.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.55.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.55.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.55.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.56.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.56.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.56.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.56.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.57.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.57.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.57.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.57.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.58.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.58.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.58.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.58.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.59.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.59.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.59.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.59.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.6.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.6.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.6.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.6.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.60.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.60.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.60.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.60.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.61.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.61.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.61.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.61.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.62.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.62.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.62.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.62.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.63.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.63.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.63.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.63.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.64.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.64.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.64.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.64.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.65.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.65.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.65.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.65.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.66.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.66.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.66.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.66.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.67.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.67.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.67.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.67.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.68.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.68.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.68.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.68.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.69.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.69.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.69.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.69.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.7.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.7.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.7.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.7.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.70.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.70.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.70.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.70.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.71.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.71.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.71.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.71.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.72.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.72.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.72.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.72.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.73.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.73.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.73.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.73.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.74.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.74.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.74.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.74.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.75.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.75.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.75.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.75.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.76.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.76.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.76.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.76.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.77.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.77.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.77.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.77.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.78.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.78.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.78.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.78.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.79.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.79.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.79.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.79.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.8.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.8.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.8.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.8.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.80.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.80.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.80.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.80.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.81.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.81.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.81.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.81.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.82.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.82.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.82.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.82.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.83.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.83.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.83.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.83.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.84.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.84.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.84.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.84.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.85.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.85.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.85.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.85.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.86.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.86.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.86.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.86.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.87.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.87.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.87.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.87.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.88.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.88.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.88.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.88.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.89.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.89.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.89.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.89.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.9.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.9.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.9.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.9.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.90.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.90.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.90.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.90.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.91.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.91.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.91.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.91.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.92.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.92.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.92.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.92.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.93.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.93.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.93.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.93.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.94.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.94.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.94.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.94.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.95.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.95.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.95.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.95.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.96.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.96.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.96.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.96.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.97.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.97.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.97.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.97.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.98.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.98.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.98.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.98.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.99.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.99.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.99.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.experts.up_proj.99.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.mlp.gate.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.k_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.k_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.k_proj.k_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.k_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.k_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.o_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.o_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.o_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.q_norm.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.q_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.q_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.q_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.v_proj.input_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.v_proj.v_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.v_proj.weight_scale": "model-00004-of-00004.safetensors", "model.language_model.layers.47.self_attn.v_proj.weight_scale_2": "model-00004-of-00004.safetensors", "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.5.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.6.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.7.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.down_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.experts.up_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.8.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.0.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.0.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.0.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.0.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.1.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.1.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.1.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.1.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.10.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.10.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.10.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.10.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.11.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.11.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.11.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.11.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.12.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.12.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.12.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.12.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.13.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.13.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.13.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.13.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.14.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.14.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.14.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.14.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.15.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.15.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.15.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.15.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.16.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.16.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.16.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.16.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.17.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.17.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.17.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.17.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.18.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.18.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.18.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.18.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.19.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.19.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.19.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.19.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.2.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.2.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.2.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.2.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.3.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.3.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.3.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.3.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.4.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.4.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.4.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.4.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.5.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.5.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.5.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.5.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.6.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.6.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.6.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.6.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.7.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.7.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.7.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.7.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.8.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.8.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.8.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.8.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.9.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.9.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.9.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.9.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.down_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.100.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.100.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.100.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.100.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.101.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.101.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.101.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.101.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.102.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.102.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.102.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.102.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.103.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.103.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.103.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.103.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.104.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.104.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.104.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.104.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.105.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.105.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.105.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.105.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.106.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.106.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.106.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.106.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.107.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.107.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.107.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.107.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.108.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.108.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.108.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.108.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.109.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.109.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.109.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.109.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.110.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.110.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.110.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.110.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.111.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.111.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.111.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.111.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.112.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.112.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.112.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.112.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.113.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.113.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.113.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.113.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.114.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.114.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.114.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.114.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.115.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.115.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.115.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.115.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.116.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.116.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.116.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.116.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.117.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.117.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.117.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.117.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.118.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.118.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.118.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.118.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.119.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.119.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.119.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.119.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.120.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.120.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.120.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.120.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.121.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.121.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.121.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.121.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.122.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.122.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.122.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.122.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.123.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.123.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.123.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.123.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.124.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.124.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.124.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.124.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.125.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.125.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.125.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.125.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.126.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.126.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.126.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.126.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.127.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.127.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.127.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.127.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.20.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.20.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.20.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.20.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.21.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.21.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.21.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.21.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.22.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.22.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.22.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.22.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.23.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.23.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.23.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.23.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.24.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.24.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.24.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.24.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.25.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.25.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.25.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.25.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.26.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.26.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.26.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.26.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.27.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.27.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.27.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.27.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.28.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.28.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.28.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.28.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.29.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.29.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.29.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.29.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.30.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.30.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.30.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.30.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.31.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.31.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.31.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.31.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.32.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.32.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.32.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.32.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.33.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.33.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.33.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.33.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.34.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.34.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.34.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.34.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.35.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.35.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.35.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.35.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.36.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.36.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.36.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.36.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.37.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.37.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.37.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.37.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.38.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.38.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.38.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.38.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.39.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.39.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.39.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.39.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.40.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.40.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.40.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.40.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.41.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.41.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.41.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.41.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.42.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.42.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.42.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.42.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.43.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.43.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.43.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.43.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.44.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.44.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.44.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.44.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.45.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.45.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.45.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.45.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.46.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.46.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.46.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.46.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.47.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.47.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.47.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.47.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.48.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.48.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.48.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.48.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.49.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.49.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.49.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.49.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.50.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.50.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.50.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.50.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.51.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.51.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.51.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.51.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.52.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.52.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.52.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.52.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.53.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.53.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.53.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.53.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.54.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.54.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.54.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.54.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.55.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.55.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.55.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.55.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.56.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.56.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.56.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.56.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.57.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.57.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.57.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.57.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.58.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.58.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.58.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.58.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.59.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.59.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.59.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.59.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.60.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.60.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.60.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.60.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.61.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.61.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.61.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.61.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.62.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.62.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.62.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.62.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.63.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.63.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.63.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.63.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.64.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.64.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.64.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.64.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.65.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.65.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.65.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.65.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.66.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.66.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.66.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.66.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.67.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.67.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.67.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.67.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.68.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.68.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.68.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.68.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.69.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.69.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.69.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.69.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.70.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.70.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.70.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.70.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.71.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.71.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.71.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.71.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.72.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.72.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.72.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.72.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.73.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.73.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.73.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.73.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.74.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.74.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.74.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.74.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.75.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.75.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.75.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.75.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.76.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.76.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.76.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.76.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.77.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.77.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.77.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.77.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.78.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.78.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.78.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.78.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.79.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.79.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.79.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.79.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.80.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.80.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.80.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.80.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.81.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.81.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.81.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.81.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.82.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.82.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.82.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.82.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.83.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.83.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.83.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.83.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.84.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.84.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.84.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.84.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.85.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.85.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.85.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.85.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.86.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.86.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.86.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.86.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.87.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.87.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.87.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.87.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.88.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.88.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.88.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.88.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.89.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.89.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.89.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.89.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.90.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.90.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.90.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.90.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.91.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.91.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.91.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.91.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.92.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.92.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.92.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.92.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.93.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.93.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.93.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.93.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.94.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.94.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.94.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.94.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.95.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.95.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.95.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.95.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.96.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.96.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.96.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.96.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.97.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.97.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.97.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.97.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.98.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.98.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.98.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.98.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.99.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.99.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.99.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.gate_proj.99.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.0.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.0.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.0.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.0.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.1.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.1.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.1.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.1.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.10.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.10.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.10.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.10.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.100.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.100.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.100.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.100.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.101.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.101.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.101.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.101.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.102.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.102.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.102.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.102.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.103.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.103.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.103.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.103.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.104.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.104.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.104.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.104.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.105.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.105.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.105.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.105.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.106.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.106.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.106.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.106.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.107.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.107.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.107.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.107.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.108.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.108.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.108.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.108.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.109.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.109.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.109.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.109.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.11.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.11.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.11.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.11.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.110.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.110.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.110.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.110.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.111.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.111.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.111.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.111.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.112.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.112.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.112.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.112.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.113.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.113.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.113.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.113.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.114.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.114.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.114.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.114.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.115.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.115.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.115.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.115.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.116.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.116.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.116.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.116.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.117.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.117.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.117.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.117.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.118.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.118.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.118.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.118.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.119.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.119.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.119.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.119.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.12.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.12.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.12.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.12.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.120.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.120.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.120.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.120.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.121.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.121.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.121.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.121.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.122.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.122.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.122.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.122.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.123.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.123.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.123.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.123.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.124.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.124.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.124.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.124.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.125.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.125.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.125.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.125.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.126.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.126.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.126.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.126.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.127.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.127.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.127.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.127.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.13.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.13.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.13.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.13.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.14.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.14.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.14.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.14.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.15.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.15.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.15.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.15.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.16.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.16.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.16.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.16.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.17.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.17.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.17.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.17.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.18.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.18.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.18.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.18.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.19.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.19.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.19.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.19.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.2.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.2.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.2.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.2.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.20.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.20.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.20.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.20.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.21.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.21.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.21.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.21.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.22.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.22.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.22.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.22.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.23.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.23.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.23.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.23.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.24.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.24.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.24.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.24.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.25.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.25.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.25.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.25.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.26.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.26.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.26.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.26.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.27.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.27.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.27.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.27.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.28.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.28.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.28.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.28.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.29.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.29.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.29.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.29.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.3.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.3.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.3.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.3.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.30.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.30.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.30.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.30.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.31.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.31.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.31.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.31.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.32.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.32.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.32.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.32.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.33.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.33.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.33.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.33.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.34.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.34.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.34.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.34.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.35.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.35.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.35.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.35.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.36.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.36.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.36.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.36.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.37.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.37.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.37.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.37.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.38.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.38.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.38.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.38.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.39.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.39.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.39.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.39.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.4.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.4.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.4.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.4.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.40.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.40.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.40.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.40.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.41.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.41.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.41.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.41.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.42.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.42.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.42.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.42.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.43.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.43.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.43.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.43.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.44.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.44.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.44.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.44.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.45.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.45.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.45.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.45.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.46.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.46.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.46.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.46.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.47.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.47.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.47.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.47.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.48.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.48.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.48.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.48.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.49.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.49.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.49.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.49.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.5.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.5.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.5.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.5.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.50.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.50.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.50.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.50.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.51.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.51.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.51.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.51.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.52.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.52.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.52.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.52.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.53.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.53.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.53.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.53.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.54.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.54.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.54.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.54.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.55.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.55.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.55.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.55.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.56.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.56.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.56.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.56.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.57.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.57.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.57.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.57.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.58.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.58.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.58.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.58.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.59.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.59.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.59.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.59.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.6.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.6.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.6.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.6.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.60.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.60.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.60.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.60.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.61.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.61.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.61.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.61.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.62.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.62.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.62.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.62.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.63.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.63.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.63.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.63.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.64.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.64.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.64.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.64.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.65.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.65.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.65.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.65.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.66.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.66.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.66.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.66.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.67.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.67.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.67.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.67.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.68.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.68.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.68.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.68.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.69.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.69.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.69.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.69.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.7.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.7.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.7.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.7.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.70.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.70.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.70.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.70.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.71.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.71.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.71.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.71.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.72.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.72.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.72.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.72.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.73.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.73.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.73.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.73.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.74.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.74.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.74.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.74.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.75.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.75.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.75.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.75.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.76.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.76.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.76.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.76.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.77.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.77.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.77.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.77.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.78.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.78.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.78.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.78.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.79.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.79.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.79.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.79.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.8.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.8.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.8.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.8.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.80.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.80.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.80.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.80.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.81.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.81.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.81.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.81.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.82.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.82.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.82.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.82.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.83.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.83.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.83.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.83.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.84.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.84.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.84.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.84.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.85.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.85.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.85.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.85.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.86.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.86.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.86.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.86.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.87.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.87.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.87.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.87.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.88.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.88.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.88.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.88.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.89.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.89.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.89.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.89.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.9.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.9.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.9.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.9.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.90.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.90.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.90.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.90.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.91.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.91.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.91.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.91.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.92.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.92.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.92.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.92.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.93.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.93.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.93.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.93.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.94.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.94.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.94.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.94.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.95.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.95.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.95.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.95.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.96.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.96.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.96.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.96.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.97.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.97.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.97.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.97.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.98.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.98.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.98.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.98.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.99.input_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.99.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.99.weight_scale": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.experts.up_proj.99.weight_scale_2": "model-00002-of-00004.safetensors", "model.language_model.layers.9.mlp.gate.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.k_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.k_proj.k_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.k_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.o_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.o_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.q_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.q_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.v_proj.input_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.v_proj.v_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00004.safetensors", "model.language_model.layers.9.self_attn.v_proj.weight_scale_2": "model-00001-of-00004.safetensors", "model.language_model.norm.weight": "model-00004-of-00004.safetensors", "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors", "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors", "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors", "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors", "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors", "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors", "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors", "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors", "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors", "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors", "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors", "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors", "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors" } }